© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 113319
    Prev
    Next
    INDEX
    Explanations

    Code snippets/documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wenn
    -0.07
     gir
    -0.07
    למיד
    -0.07
    tax
    -0.07
     dictated
    -0.07
    zn
    -0.07
    gir
    -0.07
     econom
    -0.07
     Traveling
    -0.07
    מצ
    -0.07
    POSITIVE LOGITS
     آپ
    0.09
    🏼
    0.08
    obia
    0.08
    (Duration
    0.08
     Frankie
    0.08
     неаб
    0.08
    vereniging
    0.08
     dalk
    0.08
     Olu
    0.07
    niku
    0.07
    Activations Density 0.012%

    No Known Activations